Abstract — Control and optimization of acoustic sensors can significantly impact the effectiveness of sonar deployment in variable and uncertain underwater environments. On the other hand, the design of optimal control systems requires tractable models of system dynamics, which in this case include acoustic-wave propagation phenomena. High-fidelity acoustic models that capture the influence of environmental conditions on wave propagation involve partial differential equations (PDEs), and are computationally intensive. Also, by relying on the numerical solution of PDEs for given boundary and initial conditions, they do not provide closed-form functional forms for the propagation loss or other output variables. In this paper, a simple Bayesian network (BN) model of acoustic propagation is presented for use in sonar control. The performance of the BN model compares favorably to that of a radial basis function neural network. Additionally, the sensor range dependency on spatial and temporal coordinates can be estimated and utilized to compute optimal sonar control strategies. I.

Particle swarm inversion of large neural networks is a com-putationally intensive process. By the implementing a modified particle swarm optimizer and neural network in reconfigurable hardware, many of the computations can be preformed simultaneously, significantly reducing computa-tion time compared to a conventional computer. 1.

Abstract—Implementation of real-time neural network inver-sion on the SRC-6e, a computer that uses multiple field-pro-grammable gate arrays (FPGAs) as reconfigurable computing elements, is examined using a sonar application as a specific case study. A feedforward multilayer perceptron neural network is used to estimate the performance of the sonar system (Jung et al., 2001). A particle swarm algorithm uses the trained network to perform a search for the control parameters required to optimize the output performance of the sonar system in the presence of imposed environmental constraints (Fox et al., 2002). The particle swarm optimization (PSO) requires repetitive queries of the neural network. Alternatives for implementing neural networks and particle swarm algorithms in reconfigurable hardware are contrasted. The final implementation provides nearly two orders of magnitude of speed increase over a state-of-the-art personal computer (PC), providing a real-time solution. Index Terms—Field-programmable gate arrays (FPGAs), in-verse problems, neural network hardware, particle swarm theory, real-time systems, reconfigurable architectures, sonar. I.